CN107742127A - A kind of improved anti-electricity-theft intelligent early-warning system and method - Google Patents
A kind of improved anti-electricity-theft intelligent early-warning system and method Download PDFInfo
- Publication number
- CN107742127A CN107742127A CN201710973947.4A CN201710973947A CN107742127A CN 107742127 A CN107742127 A CN 107742127A CN 201710973947 A CN201710973947 A CN 201710973947A CN 107742127 A CN107742127 A CN 107742127A
- Authority
- CN
- China
- Prior art keywords
- stealing
- electricity
- data
- warning
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000005611 electricity Effects 0.000 claims abstract description 53
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000011835 investigation Methods 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 11
- 230000006837 decompression Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 9
- 238000010168 coupling process Methods 0.000 claims description 9
- 238000005859 coupling reaction Methods 0.000 claims description 9
- 238000011002 quantification Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000001755 vocal effect Effects 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 2
- 230000008014 freezing Effects 0.000 claims 1
- 238000007710 freezing Methods 0.000 claims 1
- 210000005036 nerve Anatomy 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 10
- 238000007405 data analysis Methods 0.000 abstract description 5
- 238000004141 dimensional analysis Methods 0.000 abstract description 3
- 238000011161 development Methods 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 description 4
- 238000007418 data mining Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The present invention discloses a kind of improved anti-electricity-theft intelligent early-warning system and method, belongs to intelligent grid informatization.The system includes data source modules, memory module, diagnostic module, warning module.This method establishes user's electricity stealing probability big data analysis model, by multi dimensional analysis, precisely identify doubtful stealing user, applied to the business of opposing electricity-stealing, solve manually to carry out opposing electricity-stealing at present monitoring, analysis, the investigation bottleneck that workload is big, precision is low, for a live line power utility check and the personnel that oppose electricity-stealing precisely, efficiently development oppose electricity-stealing and analyze and investigation work provides reliable technical support.After configuration setting, without artificial interference, Autonomy carries out precisely analysis and early warning to power system electricity stealing；Solve manually to carry out oppose electricity-stealing monitoring, analysis, the investigation bottleneck that workload is big, precision is low at present, lift the reasonability and accuracy of managing power network resources.
Description
Technical field
The invention belongs to intelligent grid informatization, more particularly to a kind of improved anti-electricity-theft intelligent early-warning system and
Method.
Background technology
In recent years, as the continuous development quickly propelled with science and technology of market economy, stealing electricity phenomenon are still prohibited not repeatly
Absolutely, stealing scope is wide, Ren Yuanduo, quantity are big, and professional, intelligent spreading trend is presented, situation of opposing electricity-stealing very severe, this
Intelligent electricity anti-theft early warning system is directed to establishing wisdom energy system, technology and the system of power grid enterprises, establishes power business profit
The ecosystem of beneficial relative benign cycle and value win-win.
At present with producing abnormal alarm data largely relevant with stealing in extraction system, line loss system, but may not report
Warn and there is stealing problem, it is impossible to accomplished manually to be analyzed from door to door or each household all arrives scene investigation, prior art application
What the A of publication No. CN 106291253 were analyzed based on the event data to acquisition terminal and electric energy meter generation, place one's entire reliance upon
Acquisition terminal and electric energy meter are to the record information of event, and data acquisition channel and analysis mode are excessively single, and this results in work as and adopted
When collecting terminal and electric energy meter event data record inaccuracy, very big error is caused to analysis result, when time record data is lost
When, stealing analysis can not be carried out.
Based on above mentioned problem, user's electricity stealing probability big data analysis model need to be established, by multi dimensional analysis, precisely
Doubtful stealing user is identified, applied to the business of opposing electricity-stealing, solves manually to carry out oppose electricity-stealing monitoring, analysis, investigation workload at present
Greatly, the low bottleneck of precision, oppose electricity-stealing analysis and investigation precisely, are efficiently carried out for one line power utility check of scene and the personnel that oppose electricity-stealing
Work provides reliable technical support.
The content of the invention
In view of the shortcomings of the prior art, it is an object of the invention to provide a kind of improved anti-electricity-theft intelligent early-warning system, match somebody with somebody
Install after determining, without artificial interference, Autonomy carries out precisely analysis and early warning to power system electricity stealing；Solves current people
Work oppose electricity-stealing monitoring, analysis, the investigation bottleneck that workload is big, precision is low, lifted managing power network resources reasonability and
Accuracy.
To achieve these goals, an aspect of of the present present invention provides a kind of improved anti-electricity-theft intelligent early-warning system, should
System includes data source modules, memory module, diagnostic module, warning module, and wherein data source modules are connected with memory module, deposited
Storage module is connected with diagnostic module, and diagnostic module is connected with warning module.
The data source modules：It is the data source of analysis and warning data, the module passes through collecting device, vocational window
Electric power associated traffic data is obtained etc. mode.
The memory module：Storage obtains to obtain archives class data, exception class data, measurement class number from each system of data source
According to the sample data in, credit data and sample storehouse etc..
The diagnostic module：It is the core of abnormal data screening and analysis, is based primarily upon a diagnostic model and two
Secondary diagnostic model, abnormal data is carried out gradually to screen and position.Pass through abnormal data and file data, metric data, sample
Storehouse data are associated and compared analysis, the doubtful stealing user of precise positioning.
The warning module：By visualized graph interface and report interface to a live line power utility check and the people that opposes electricity-stealing
Member provides the warning information of doubtful stealing user, and reliable skill is provided precisely, efficiently to carry out to oppose electricity-stealing analysis and investigate and prosecute work
Art supports.
To achieve these goals, another aspect provides a kind of improved anti-electricity-theft intelligent early-warning method,
This method comprises the following steps：
Step 1：By data source modules, custom power information acquisition terminal information, including user's electric energy meter record are obtained
Electricity, electric current, electric power, the implementation information such as load, pass through operation system window typing geographic information data, files on each of customers is believed
Breath, metering device archive information and harvester archive information etc..
Step 2：Dependency number is obtained by data memory module, power information acquisition system is per diem obtained and freezes day to count
According to, monthly obtain sales service marketing application system, GIS-Geographic Information System, magnanimity file data information, the credit of line loss system
Data, abnormal data, line loss data etc..
Step 3：" stealing coupling index system " model is built, data are analyzed, handle the corresponding index spy of generation
Value indicative.Index feature value includes：Electricity trend, capacity conversion, line loss trend, decompression, defluidization, backward walking, uncap, unpack, electromagnetism
Interference etc..
" the stealing coupling index system " model, Liaoning electric power saving is netted according to measuring principle/stealing mode and with reference to state
The characteristics of Co., Ltd's user's stealing, to stealing user over the years in the number such as collection, the electricity of marketing system, voltage, electric current, alarm
According to reversely being analyzed, stealing coupling index system is determined, meets that electricity stealing diagnosis requires that specific targets are as follows with identification：
(1) electric quantity change
" electric quantity change index " can react the feature that stealing is carried out by changing measurement loop, and the feature as model refers to
Mark, the industry-specific user in portion may cause erroneous judgement in the Spring Festival and long false data, it is necessary to reject to result；Its quantitative formula is
Wherein kl is same day downward trend index, and fi is same day electricity, and fl is front and rear several days electricity, and α i are weight, before d is
Number of days afterwards.
(2) line loss changes
Line loss growth rate Y and theory wire loss are compared into difference G and are weighted processing to quantify line losses indices.
E=α Y+ β G
Wherein α is weight shared by Y, and β is weight shared by G.
(3) decompression
Abnormal frequency is more, and the alarm reliability is higher, the accounting of abnormity point will occur in the cycle as model
Characteristic index, its quantitative formula are
Wherein K counts to be abnormal, and Q counts for valid data.
(4) defluidization
Abnormal frequency is more, and the alarm reliability is higher, the accounting of abnormity point will occur in the cycle as model
Characteristic index, its quantitative formula are
Wherein K counts to be abnormal, and Q counts for valid data.
(5) uncap, unpack, backward walking, electromagnetic interference
The alarm of event class (is uncapped, unpacked, magnetic interference)：Alarm class event whether is produced in the measuring point cycle and enters row index
Quantification treatment
Electricity exception class alerts (backward walking)：Quantification of targets processing is carried out according to backward walking number in the measuring point cycle
K is record number in the nearly cycle
(6) stealing, arrearage
Stealing/arrearage record number will occur in nearest 3 years and carry out quantification of targets processing
K is to occur within nearly 3 years to disobey to steal (arrearage) record number
Step 4：By diagnostic module, system passes through in judgment models of index feature value input pointer of generation
Neural network algorithm determines whether doubtful stealing information, the step initial analysis abnormal data and doubtful stealing data, reduces
The pseudo- stealing information caused by gathered data quality problems.
Data judgment models (the preliminary doubtful stealing user model of examination)：
At present with producing abnormal alarm data largely relevant with stealing in extraction system, line loss system, but may not alarm
It there is stealing problem, it is impossible to it is artificial to be analyzed from door to door or each household all arrive scene investigation, big data need to be used to excavate calculation
Method carries out data mining and examination goes out doubtful stealing user.The present invention is opposed electricity-stealing using sorting algorithm and processing business, selection are determined
Plan tree method, method are as follows：
(1) " electricity, line loss judge " node, if it is judged that meeting decision rule, is then used for the doubtful stealing of one-level
Family, into device exception decision node, if it is judged that it is then normal not meet, next node judgement is not entered.
【Rule of judgment：Electric quantity change>Threshold value 1 or line loss change>Threshold value 2】
(2) " electricity, line loss judge " node is judged to the result met, " device judges extremely " node is brought into, if sentenced
Disconnected result meets decision rule, then is the doubtful user of two level, into " arrearage, stealing judge " node, if it is judged that not being inconsistent
Conjunction is then that the node is normal, does not enter next node judgement.
【Rule of judgment：Decompression index>Threshold value 3 or defluidization index>Threshold value 4 or event index=1】
(3) " device judges extremely " node is judged to the result met, " arrearage, stealing judge " node is brought into, if sentenced
Disconnected result meets judgment rule, then is the doubtful user of three-level, is judged as stealing substantially, if it is judged that not meeting, is, should
Node is normal.
【Rule of judgment：Stealing index>Threshold value 5 or arrearage index>Threshold value 6】
Step 5：By diagnostic module, system once doubtful stealing information will be inputted in secondary judgment models, further fixed
The doubtful stealing user in position.
Further to improve the accuracy of doubtful stealing user anticipation, used greatly for the doubtful stealing user of preliminary examination
Whether the electricity consumption track that data analysis technique further verifies the user deviate from normal electricity consumption track, if the deviation from then
Further confirm that the user has stealing suspicion.
The normal electricity consumption track of user is found it is necessary to by the substantial amounts of day power load curve of user's history cluster
Go out.The system clusters big data analytical technology using K-Means.
Confirm whether user deviate from normal electricity consumption track, be exactly that the daily load curve of the family monitoring cycle is same with it
The normal characteristics curve in season is drawn after being compared.The system is using discrete Fu Leixie apart from big data analytical technology
(being used to calculate different similarity of curves) is compared, and analyzes the drift rate of its electricity consumption behavior, so as to which further positioning is doubted
Like stealing user.
Step 6：Element is alerted in a manner of information notice information system, early warning is initiated to doubtful stealing user, by
With inspection, personnel carry out on-site verification, evidence obtaining, investigation and feedback, final to determine stealing user, and realization is remedied electricity, the electricity charge, retrieved
The economic loss of Utilities Electric Co..
Beneficial effect
The present invention establishes user's electricity stealing probability big data analysis model, by multi dimensional analysis, precisely identifies doubtful
Stealing user, applied to the business of opposing electricity-stealing, solve manually to carry out at present to oppose electricity-stealing monitoring, analysis, investigate workload greatly, precision
Low bottleneck, precisely, efficiently carry out to oppose electricity-stealing analysis and investigate and prosecute work providing for a live line power utility check and the personnel that oppose electricity-stealing
Reliable technical support.After configuration setting, without artificial interference, Autonomy is precisely analyzed power system electricity stealing
And early warning；Solve manually to carry out oppose electricity-stealing monitoring, analysis, the investigation bottleneck that workload is big, precision is low at present, lifting power network money
The reasonability and accuracy of source control.
Brief description of the drawings
Fig. 1 is the improved anti-electricity-theft intelligent early-warning system frame diagram of one kind provided by the invention.
Fig. 2 is a determination methods flow chart provided by the invention.
Fig. 3, which is that one kind provided by the invention is secondary, judges load curve comparison chart.
Embodiment
As shown in figure 1, the invention provides a kind of improved anti-electricity-theft intelligent early-warning system, the system includes data source mould
Block, memory module, diagnostic module, warning module, wherein data source modules are connected with memory module, memory module and diagnostic module
It is connected, diagnostic module is connected with warning module.
The data source modules：It is the data source of analysis and warning data, the module passes through collecting device, vocational window
Electric power associated traffic data, including sales service application system, power information acquisition system, line loss management system of local electric network are obtained etc. mode
Data.
The memory module：Storage obtains to obtain archives class data, exception class data, measurement class number from each system of data source
According to the sample data in, credit data and sample storehouse etc..
The diagnostic module：It is the core of abnormal data screening and analysis, is based primarily upon a diagnostic model and two
Secondary diagnostic model, abnormal data is carried out gradually to screen and position.Pass through abnormal data and file data, metric data, sample
Storehouse data are associated and compared analysis, the doubtful stealing user of precise positioning.
The warning module：By visualized graph interface and report interface to a live line power utility check and the people that opposes electricity-stealing
Member provides the warning information of doubtful stealing user, and reliable skill is provided precisely, efficiently to carry out to oppose electricity-stealing analysis and investigate and prosecute work
Art supports.
Another aspect provides a kind of improved anti-electricity-theft intelligent early-warning method, this method includes following step
Suddenly：
Step 1：By data source modules, custom power information acquisition terminal information, including user's electric energy meter record are obtained
Electricity, electric current, electric power, the implementation information such as load, pass through operation system window typing geographic information data, files on each of customers is believed
Breath, metering device archive information and harvester archive information etc..
Step 2：Dependency number is obtained by data memory module, power information acquisition system is per diem obtained and freezes day to count
According to, monthly obtain sales service marketing application system, GIS-Geographic Information System, magnanimity file data information, the credit of line loss system
Data, abnormal data, line loss data etc..
Step 3：" stealing coupling index system " model is built, data are analyzed, handle the corresponding index spy of generation
Value indicative.Index feature value includes：Electricity trend, capacity conversion, line loss trend, decompression, defluidization, backward walking, uncap, unpack, electromagnetism
Interference etc..
" the stealing coupling index system " model, Liaoning electric power saving is netted according to measuring principle/stealing mode and with reference to state
The characteristics of Co., Ltd's user's stealing, to stealing user over the years in the number such as collection, the electricity of marketing system, voltage, electric current, alarm
According to reversely being analyzed, stealing coupling index system is determined, meets that electricity stealing diagnosis requires that specific targets are as follows with identification：
(1) electric quantity change
" electric quantity change index " can react the feature that stealing is carried out by changing measurement loop, and the feature as model refers to
Mark, the industry-specific user in portion may cause erroneous judgement in the Spring Festival and long false data, it is necessary to reject to result；Its quantitative formula is
Wherein kl is same day downward trend index, and fi is same day electricity, and fl is front and rear several days electricity, and α i are weight, before d is
Number of days afterwards.
(2) line loss changes
Line loss growth rate Y and theory wire loss are compared into difference G and are weighted processing to quantify line losses indices.
E=α Y+ β G
Wherein α is weight, preferably 40% shared by Y.β is weight, preferably 60% shared by G.
(3) decompression
Abnormal frequency is more, and the alarm reliability is higher, the accounting of abnormity point will occur in the cycle as model
Characteristic index, its quantitative formula are
Wherein K counts to be abnormal, and Q counts for valid data.
(4) defluidization
Abnormal frequency is more, and the alarm reliability is higher, the accounting of abnormity point will occur in the cycle as model
Characteristic index, its quantitative formula are
Wherein K counts to be abnormal, and Q counts for valid data.
(5) uncap, unpack, backward walking, electromagnetic interference
The alarm of event class (is uncapped, unpacked, magnetic interference)：Alarm class event whether is produced in the measuring point cycle and enters row index
Quantification treatment
Electricity exception class alerts (backward walking)：Quantification of targets processing is carried out according to backward walking number in the measuring point cycle
K is record number in the nearly cycle
(6) stealing, arrearage
Stealing/arrearage record number will occur in nearest 3 years and carry out quantification of targets processing
K is to occur within nearly 3 years to disobey to steal (arrearage) record number
Step 4：By diagnostic module, system passes through in judgment models of index feature value input pointer of generation
Neural network algorithm determines whether doubtful stealing information, the step initial analysis abnormal data and doubtful stealing data, reduces
The pseudo- stealing information caused by gathered data quality problems.
Data judgment models (the preliminary doubtful stealing user model of examination)：
At present with producing abnormal alarm data largely relevant with stealing in extraction system, line loss system, but may not alarm
It there is stealing problem, it is impossible to it is artificial to be analyzed from door to door or each household all arrive scene investigation, big data need to be used to excavate calculation
Method carries out data mining and examination goes out doubtful stealing user.According to substantial amounts of Data Mining and stealing analysis of cases, we use
Sorting algorithm is opposed electricity-stealing and processing business, trade-off decision tree method, as shown in Fig. 2 this method is as follows：
(1) " electricity, line loss judge " node, if it is judged that meeting decision rule, is then used for the doubtful stealing of one-level
Family, into device exception decision node, if it is judged that it is then normal not meet, next node judgement is not entered.
【Rule of judgment：Electric quantity change>Threshold value 1 or line loss change>Threshold value 2】
(2) " electricity, line loss judge " node is judged to the result met, " device judges extremely " node is brought into, if sentenced
Disconnected result meets decision rule, then is the doubtful user of two level, into " arrearage, stealing judge " node, if it is judged that not being inconsistent
Conjunction is then that the node is normal, does not enter next node judgement.
【Rule of judgment：Decompression index>Threshold value 3 or defluidization index>Threshold value 4 or event index=1】
(3) " device judges extremely " node is judged to the result met, " arrearage, stealing judge " node is brought into, if sentenced
Disconnected result meets judgment rule, then is the doubtful user of three-level, is judged as stealing substantially, if it is judged that not meeting, is, should
Node is normal.
【Rule of judgment：Stealing index>Threshold value 5 or arrearage index>Threshold value 6】
Step 5：By diagnostic module, system once doubtful stealing information will be inputted in secondary judgment models, further fixed
The doubtful stealing user in position.
Further to improve the accuracy of doubtful stealing user anticipation, used greatly for the doubtful stealing user of preliminary examination
Whether the electricity consumption track that data analysis technique further verifies the user deviate from normal electricity consumption track, if the deviation from then
Further confirm that the user has stealing suspicion.
The normal electricity consumption track of user is found it is necessary to by the substantial amounts of day power load curve of user's history cluster
Go out.The system clusters big data analytical technology, the day electricity consumption to user's history 2-3 Various Seasonals using K-Means
Load curve is clustered, and the abnormal curve that wherein few day power load is clustered out is rejected, a large amount of day power load clusters
Go out normal characteristics curve of the curve as the user.
Confirm whether user deviate from normal electricity consumption track, be exactly that the daily load curve of the family monitoring cycle is same with it
The normal characteristics curve in season is drawn after being compared.The system is using discrete Fu Leixie apart from big data analytical technology
(being used to calculate different similarity of curves) is compared, and analyzes the drift rate of its electricity consumption behavior, so as to which further positioning is doubted
Like stealing user.
As shown in figure 3, history power load indicatrix is clustered using K-Means clustering algorithms, using discrete Fu Leixie
Distance algorithm compares load curve, and Fig. 3 clusters out certain to the doubtful stealing user of certain preliminary examination using K-Means clustering algorithms
The normal day power load indicatrix of the class of season 4, it is by discrete Fu Leixie distance algorithms that the daily load of the family monitoring cycle is bent
After line is compared with this 4 class curve, obtain a result as follows：
1st, with the 1st cluster distance：1095>Ultimate range 330 between 1 class
2nd, with the 2nd cluster distance：599>Ultimate range 165 between 2 classes
3rd, with the 3rd cluster distance：312>Ultimate range 144 between 3 classes
4th, with the 4th cluster distance：811>Ultimate range 201 between 4 classes
As can be seen that the daily load curve data of user's monitoring cycle are born from day electricity consumption more normal than 4 classes with a distance from barycenter
Lotus Characteristic Curve data will be big from the ultimate range of barycenter, illustrates that the customer charge characteristic enters a new state, has very
Big probability is to enter stealing state.
Step 6：Element is alerted in a manner of information notice information system, early warning is initiated to doubtful stealing user, by
With inspection, personnel carry out on-site verification, evidence obtaining, investigation and feedback, final to determine stealing user, and realization is remedied electricity, the electricity charge, retrieved
The economic loss of Utilities Electric Co..
Claims (10)
- A kind of 1. improved anti-electricity-theft intelligent early-warning system, it is characterised in that the system include data source modules, memory module, Diagnostic module, warning module, wherein data source modules are connected with memory module, and memory module is connected with diagnostic module, diagnose mould Block is connected with warning module；The data source modules：It is the data source of analysis and warning data, the module passes through collecting device, vocational window mode Obtain electric power associated traffic data；The memory module：Storage obtained from each system of data source archives class data, exception class data, measure class data, Credit data and the sample data in sample storehouse；The diagnostic module：It is the core of abnormal data screening and analysis, based on a diagnostic model and secondary diagnosis mould Type, abnormal data is carried out gradually to screen and position；Entered by abnormal data and file data, metric data, sample storehouse data Row association and comparison analysis, the doubtful stealing user of precise positioning；The warning module：Carried by visualized graph interface and report interface to a live line power utility check and the personnel of opposing electricity-stealing For the warning information of doubtful stealing user.
- A kind of 2. improved anti-electricity-theft intelligent early-warning method, it is characterised in that using above-mentioned a kind of based on the thief-proof of electric power big data Electric intelligent early-warning system, this method comprise the following steps：Step 1：By data source modules, custom power information acquisition terminal information is obtained；Step 2：Dependency number is obtained by data memory module, the day freezing data of power information acquisition system is per diem obtained, presses Month obtain sales service marketing application system, GIS-Geographic Information System, the magnanimity file data information of line loss system, credit data, Abnormal data, line loss data；Step 3：" stealing coupling index system " model is built, data are analyzed, handle the corresponding index feature of generation Value；Step 4：By diagnostic module, system passes through nerve by judgment models of index feature value input pointer of generation Network algorithm determines whether doubtful stealing information, initial analysis abnormal data and doubtful stealing data；Step 5：By diagnostic module, system once doubtful stealing information will be inputted in secondary judgment models, and further positioning is doubted Like stealing user；Step 6：Element is alerted in a manner of information notice information system, early warning is initiated to doubtful stealing user, by with inspection Personnel carry out on-site verification, evidence obtaining, investigation and feedback, final to determine stealing user, and realization remedies electricity, the electricity charge, retrieves electric power The economic loss of company.
- A kind of 3. improved anti-electricity-theft intelligent early-warning method as claimed in claim 2, it is characterised in that methods described step 1 Electricity, electric current, electric power, load implementation information including user's electric energy meter record, pass through operation system window typing geography information Data, User Profile information, metering device archive information and harvester archive information.
- A kind of 4. improved anti-electricity-theft intelligent early-warning method as claimed in claim 2, it is characterised in that index described in step 3 Characteristic value includes：Electricity trend, capacity conversion, line loss trend, decompression, defluidization, backward walking, uncap, unpack, electromagnetic interference.
- 5. a kind of improved anti-electricity-theft intelligent early-warning method as described in claim 2 or 4, it is characterised in that described in step 3 " stealing coupling index system " model, index include：Electric quantity change, line loss change, decompression, defluidization, uncap, unpack, backward walking, electricity Magnetic disturbance, stealing, arrearage.
- A kind of 6. improved anti-electricity-theft intelligent early-warning method as described in claim 2 or 4 or 5, it is characterised in that step 3 institute " stealing coupling index system " model is stated, specific quantitative formula is：(1) electric quantity changeIts quantitative formula isWherein kl is same day downward trend index, and fi is same day electricity, and fl is front and rear several days electricity, and α i are weight, and d is front and rear day Number；(2) line loss changesIts quantitative formula isE=α Y+ β GWherein α is weight shared by Y, and β is weight shared by G；(3) decompressionIts quantitative formula isWherein K counts to be abnormal, and Q counts for valid data.(4) defluidizationIts quantitative formula isWherein K counts to be abnormal, and Q counts for valid data.(5) uncap, unpack, backward walking, electromagnetic interferenceThe alarm of event class (is uncapped, unpacked, magnetic interference)：Alarm class event whether is produced in the measuring point cycle and carries out quantification of targets ProcessingElectricity exception class alerts (backward walking)：Quantification of targets processing is carried out according to backward walking number in the measuring point cycleK is record number in the nearly cycle(6) stealing, arrearageStealing/arrearage record number will occur in nearest 3 years and carry out quantification of targets processingK is to occur within nearly 3 years to disobey to steal (arrearage) record number.
- 7. a kind of improved anti-electricity-theft intelligent early-warning method as claimed in claim 2, it is characterised in that described in step 4 once Data judgment models, i.e., the preliminary doubtful stealing user model of examination use traditional decision-tree.
- A kind of 8. improved anti-electricity-theft intelligent early-warning method as claimed in claim 7, it is characterised in that decision-making described in step 4 Tree method comprises the following steps that：(1) " electricity, line loss judge " node, if it is judged that meeting decision rule, is then the doubtful stealing user of one-level, enters Enter device exception decision node, if it is judged that it is then normal not meet, do not enter next node judgement；Rule of judgment：Electric quantity change>Threshold value 1 or line loss change>Threshold value 2；(2) judges " electricity, line loss judge " node the result met, " device judges extremely " node is brought into, if it is determined that knot Fruit meets decision rule, then is the doubtful user of two level, into " arrearage, stealing judge " node, if it is judged that not meeting then For the node is normal, does not enter next node judgement；Rule of judgment：Decompression index>Threshold value 3 or defluidization index>Threshold value 4 or event index=1；(3) " device judges extremely " node is judged to the result met, " arrearage, stealing judge " node is brought into, if it is determined that knot Fruit meets judgment rule, then is the doubtful user of three-level, is judged as stealing substantially, if it is judged that not meeting, is, the node Normally；Rule of judgment：Stealing index>Threshold value 5 or arrearage index>Threshold value 6.
- 9. a kind of improved anti-electricity-theft intelligent early-warning method as claimed in claim 2, it is characterised in that secondary described in step 5 Judgment models, big data analytical technique is clustered using K-Means.
- 10. a kind of improved anti-electricity-theft intelligent early-warning method as claimed in claim 2, it is characterised in that step 5 uses Discrete Fu Leixie is compared apart from big data analytical technology, analyzes the drift rate of its electricity consumption behavior, further positions doubtful Stealing user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710973947.4A CN107742127B (en) | 2017-10-19 | 2017-10-19 | Improved electricity stealing prevention intelligent early warning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710973947.4A CN107742127B (en) | 2017-10-19 | 2017-10-19 | Improved electricity stealing prevention intelligent early warning system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107742127A true CN107742127A (en) | 2018-02-27 |
| CN107742127B CN107742127B (en) | 2021-06-08 |
Family
ID=61236932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710973947.4A Active CN107742127B (en) | 2017-10-19 | 2017-10-19 | Improved electricity stealing prevention intelligent early warning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107742127B (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734602A (en) * | 2018-04-09 | 2018-11-02 | 广东电网有限责任公司 | A kind of user's electricity stealing identification system based on higher-dimension random matrix |
| CN108732528A (en) * | 2018-05-28 | 2018-11-02 | 国网福建省电力有限公司电力科学研究院 | A kind of digitalized electrical energy meter method for diagnosing faults based on depth confidence network |
| CN109063929A (en) * | 2018-08-29 | 2018-12-21 | 广东电网有限责任公司 | It opposes electricity-stealing analysis and early warning method, apparatus and computer readable storage medium |
| CN109190916A (en) * | 2018-08-09 | 2019-01-11 | 国网浙江桐庐县供电有限公司 | Method of opposing electricity-stealing based on big data analysis |
| CN109444496A (en) * | 2018-10-22 | 2019-03-08 | 国网山东省电力公司滨州市滨城区供电公司 | A kind of electric power stealing detection prompt system and method |
| CN109596165A (en) * | 2018-11-23 | 2019-04-09 | 湖南城市学院 | A kind of intelligence geography information dynamic early-warning is deployed to ensure effective monitoring and control of illegal activities system and method |
| CN109615004A (en) * | 2018-12-07 | 2019-04-12 | 江苏瑞中数据股份有限公司 | A kind of anti-electricity-theft method for early warning of multisource data fusion |
| CN109753989A (en) * | 2018-11-18 | 2019-05-14 | 韩霞 | Power consumer electricity stealing analysis method based on big data and machine learning |
| CN109885559A (en) * | 2019-01-23 | 2019-06-14 | 长春工程学院 | A kind of stealing user discovery method based on the analysis of user's sample data difference characteristic |
| CN109933605A (en) * | 2019-03-08 | 2019-06-25 | 广东电网有限责任公司 | Electricity charge mistake checks method, apparatus and electronic equipment |
| CN109977984A (en) * | 2018-11-06 | 2019-07-05 | 国网新疆电力有限公司电力科学研究院 | Stealing user's judgment method based on support vector machines |
| CN110083986A (en) * | 2019-05-21 | 2019-08-02 | 国网湖南省电力有限公司 | Electrified energy-consuming device, which is opposed electricity-stealing, again simulates monitoring method, system, equipment and medium |
| CN110082579A (en) * | 2019-05-21 | 2019-08-02 | 国网湖南省电力有限公司 | A kind of area's Intelligent power-stealing prevention monitoring method, system, equipment and medium |
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
| CN110119421A (en) * | 2019-04-03 | 2019-08-13 | 昆明理工大学 | A kind of electric power stealing user identification method based on Spark flow sorter |
| CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
| CN110543499A (en) * | 2019-08-22 | 2019-12-06 | 云南电网有限责任公司 | Anti-electricity-stealing location tracking equipment based on multi-source data fusion |
| CN110968838A (en) * | 2019-11-29 | 2020-04-07 | 国网吉林省电力有限公司电力科学研究院 | Power utilization abnormity analysis method based on intelligent electric energy meter uncovering event |
| CN111008193A (en) * | 2019-12-03 | 2020-04-14 | 国网天津市电力公司电力科学研究院 | Data cleaning and quality evaluation method and system |
| CN111539843A (en) * | 2020-04-17 | 2020-08-14 | 国网新疆电力有限公司电力科学研究院 | Data-driven intelligent early warning method for preventing electricity stealing |
| CN111650432A (en) * | 2020-07-14 | 2020-09-11 | 国网冀北电力有限公司 | Line loss-based electricity stealing determination method and device |
| CN112215721A (en) * | 2020-09-04 | 2021-01-12 | 国网青海省电力公司信息通信公司 | Electric power electricity stealing accurate identification and electricity stealing feedback data analysis model based on big data |
| CN112436606A (en) * | 2020-11-26 | 2021-03-02 | 国网天津市电力公司营销服务中心 | Monitoring system for be used for anti-electricity-stealing |
| CN112632152A (en) * | 2020-12-28 | 2021-04-09 | 国网冀北电力有限公司技能培训中心 | Circuit control system based on anti-electricity-stealing practical training room |
| CN113077174A (en) * | 2021-04-21 | 2021-07-06 | 国网福建省电力有限公司 | Method for studying and judging state of sewage disposal and treatment equipment based on curve discrete Frechst distance matching |
| CN113111955A (en) * | 2021-04-21 | 2021-07-13 | 国网上海市电力公司 | Line loss abnormal data expert system and detection method |
| CN113128024A (en) * | 2021-03-17 | 2021-07-16 | 国网山东省电力公司济南供电公司 | Low-voltage electricity stealing client based on big data analysis and electricity stealing means determining method |
| CN113221931A (en) * | 2020-12-23 | 2021-08-06 | 国网吉林省电力有限公司电力科学研究院 | Electricity stealing prevention intelligent identification method based on electricity utilization information acquisition big data analysis |
| CN114076841A (en) * | 2021-11-12 | 2022-02-22 | 国网安徽省电力有限公司旌德县供电公司 | Electricity stealing behavior identification method and system based on electricity utilization information data |
| CN114881808A (en) * | 2022-04-01 | 2022-08-09 | 云南电网有限责任公司昭通供电局 | Electric power electricity stealing accurate identification method based on big data and electricity stealing prevention system |
| CN115292387A (en) * | 2022-08-18 | 2022-11-04 | 北京志翔科技股份有限公司 | Energy overrange use monitoring method based on multidimensional data analysis |
| CN116150239A (en) * | 2022-12-16 | 2023-05-23 | 彭州华润燃气有限公司 | Data mining method for gas stealing behavior |
| CN116777124A (en) * | 2023-08-24 | 2023-09-19 | 国网山东省电力公司临沂供电公司 | Power stealing monitoring method based on user power consumption behavior |
| CN116976707A (en) * | 2023-09-22 | 2023-10-31 | 安徽融兆智能有限公司 | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition |
| CN117131448A (en) * | 2023-08-25 | 2023-11-28 | 国网河南省电力公司渑池县供电公司 | Big data-based electricity stealing user intelligent identification system and method |
| CN117147959A (en) * | 2023-08-23 | 2023-12-01 | 广东电网有限责任公司佛山供电局 | Electricity larceny prevention analysis method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436705A (en) * | 2011-09-26 | 2012-05-02 | 安徽省电力公司阜阳供电公司 | Warning device for preventing electricity theft by video monitoring |
| CN102866321A (en) * | 2012-08-13 | 2013-01-09 | 广东电网公司电力科学研究院 | Self-adaptive stealing-leakage prevention diagnosis method |
| CN103675492A (en) * | 2012-09-07 | 2014-03-26 | 国网电力科学研究院 | Electricity consumption monitoring analysis method, portable electricity consumption monitoring analysis device and system |
| WO2014046530A1 (en) * | 2012-09-19 | 2014-03-27 | Grupo Tecnologías Eos S.A. De C.V. | Modular system for remotely monitoring and controling the electric power supply |
| CN104614700A (en) * | 2012-10-29 | 2015-05-13 | 江苏省电力公司常州供电公司 | Remote monitoring and diagnosing method for electric energy metering device with good real-time performance |
| CN105022021A (en) * | 2015-07-08 | 2015-11-04 | 国家电网公司 | State discrimination method for gateway electrical energy metering device based on the multiple agents |
| CN106203832A (en) * | 2016-07-12 | 2016-12-07 | 亿米特（上海）信息科技有限公司 | Intelligent electricity anti-theft analyzes system and the method for analysis |
| CN106291253A (en) * | 2016-09-23 | 2017-01-04 | 国网天津市电力公司 | A kind of anti-electricity-theft early warning analysis method |
| CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
-
2017
- 2017-10-19 CN CN201710973947.4A patent/CN107742127B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436705A (en) * | 2011-09-26 | 2012-05-02 | 安徽省电力公司阜阳供电公司 | Warning device for preventing electricity theft by video monitoring |
| CN102866321A (en) * | 2012-08-13 | 2013-01-09 | 广东电网公司电力科学研究院 | Self-adaptive stealing-leakage prevention diagnosis method |
| CN103675492A (en) * | 2012-09-07 | 2014-03-26 | 国网电力科学研究院 | Electricity consumption monitoring analysis method, portable electricity consumption monitoring analysis device and system |
| WO2014046530A1 (en) * | 2012-09-19 | 2014-03-27 | Grupo Tecnologías Eos S.A. De C.V. | Modular system for remotely monitoring and controling the electric power supply |
| CN104614700A (en) * | 2012-10-29 | 2015-05-13 | 江苏省电力公司常州供电公司 | Remote monitoring and diagnosing method for electric energy metering device with good real-time performance |
| CN105022021A (en) * | 2015-07-08 | 2015-11-04 | 国家电网公司 | State discrimination method for gateway electrical energy metering device based on the multiple agents |
| CN106203832A (en) * | 2016-07-12 | 2016-12-07 | 亿米特（上海）信息科技有限公司 | Intelligent electricity anti-theft analyzes system and the method for analysis |
| CN106291253A (en) * | 2016-09-23 | 2017-01-04 | 国网天津市电力公司 | A kind of anti-electricity-theft early warning analysis method |
| CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
Non-Patent Citations (2)
| Title |
|---|
| PARIA JOKAR ET AL: "Electricity Theft Detection in AMI Using Customers’ Consumption Patterns", 《 IEEE TRANSACTIONS ON SMART GRID》 * |
| 陈文瑛等: "应用大数据技术的反窃电分析", 《电子测量与仪器学报》 * |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734602B (en) * | 2018-04-09 | 2021-08-03 | 广东电网有限责任公司 | User electricity stealing behavior identification system based on high-dimensional random matrix |
| CN108734602A (en) * | 2018-04-09 | 2018-11-02 | 广东电网有限责任公司 | A kind of user's electricity stealing identification system based on higher-dimension random matrix |
| CN108732528A (en) * | 2018-05-28 | 2018-11-02 | 国网福建省电力有限公司电力科学研究院 | A kind of digitalized electrical energy meter method for diagnosing faults based on depth confidence network |
| CN109190916A (en) * | 2018-08-09 | 2019-01-11 | 国网浙江桐庐县供电有限公司 | Method of opposing electricity-stealing based on big data analysis |
| CN109063929A (en) * | 2018-08-29 | 2018-12-21 | 广东电网有限责任公司 | It opposes electricity-stealing analysis and early warning method, apparatus and computer readable storage medium |
| CN109444496A (en) * | 2018-10-22 | 2019-03-08 | 国网山东省电力公司滨州市滨城区供电公司 | A kind of electric power stealing detection prompt system and method |
| CN109977984A (en) * | 2018-11-06 | 2019-07-05 | 国网新疆电力有限公司电力科学研究院 | Stealing user's judgment method based on support vector machines |
| CN109977984B (en) * | 2018-11-06 | 2023-06-20 | 国网新疆电力有限公司营销服务中心(资金集约中心、计量中心) | Power stealing user judging method based on support vector machine |
| CN109753989A (en) * | 2018-11-18 | 2019-05-14 | 韩霞 | Power consumer electricity stealing analysis method based on big data and machine learning |
| CN109596165A (en) * | 2018-11-23 | 2019-04-09 | 湖南城市学院 | A kind of intelligence geography information dynamic early-warning is deployed to ensure effective monitoring and control of illegal activities system and method |
| CN109615004A (en) * | 2018-12-07 | 2019-04-12 | 江苏瑞中数据股份有限公司 | A kind of anti-electricity-theft method for early warning of multisource data fusion |
| CN109885559A (en) * | 2019-01-23 | 2019-06-14 | 长春工程学院 | A kind of stealing user discovery method based on the analysis of user's sample data difference characteristic |
| CN109885559B (en) * | 2019-01-23 | 2022-11-18 | 长春工程学院 | Electricity stealing user discovery method based on user sample data difference characteristic analysis |
| CN109933605A (en) * | 2019-03-08 | 2019-06-25 | 广东电网有限责任公司 | Electricity charge mistake checks method, apparatus and electronic equipment |
| CN110119421A (en) * | 2019-04-03 | 2019-08-13 | 昆明理工大学 | A kind of electric power stealing user identification method based on Spark flow sorter |
| CN110082579A (en) * | 2019-05-21 | 2019-08-02 | 国网湖南省电力有限公司 | A kind of area's Intelligent power-stealing prevention monitoring method, system, equipment and medium |
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
| CN110083986A (en) * | 2019-05-21 | 2019-08-02 | 国网湖南省电力有限公司 | Electrified energy-consuming device, which is opposed electricity-stealing, again simulates monitoring method, system, equipment and medium |
| CN110097297B (en) * | 2019-05-21 | 2023-08-22 | 国网湖南省电力有限公司 | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium |
| CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
| CN110543499A (en) * | 2019-08-22 | 2019-12-06 | 云南电网有限责任公司 | Anti-electricity-stealing location tracking equipment based on multi-source data fusion |
| CN110968838A (en) * | 2019-11-29 | 2020-04-07 | 国网吉林省电力有限公司电力科学研究院 | Power utilization abnormity analysis method based on intelligent electric energy meter uncovering event |
| CN111008193B (en) * | 2019-12-03 | 2023-10-31 | 国网天津市电力公司电力科学研究院 | Data cleaning and quality evaluation method and system |
| CN111008193A (en) * | 2019-12-03 | 2020-04-14 | 国网天津市电力公司电力科学研究院 | Data cleaning and quality evaluation method and system |
| CN111539843A (en) * | 2020-04-17 | 2020-08-14 | 国网新疆电力有限公司电力科学研究院 | Data-driven intelligent early warning method for preventing electricity stealing |
| CN111650432A (en) * | 2020-07-14 | 2020-09-11 | 国网冀北电力有限公司 | Line loss-based electricity stealing determination method and device |
| CN112215721A (en) * | 2020-09-04 | 2021-01-12 | 国网青海省电力公司信息通信公司 | Electric power electricity stealing accurate identification and electricity stealing feedback data analysis model based on big data |
| CN112436606A (en) * | 2020-11-26 | 2021-03-02 | 国网天津市电力公司营销服务中心 | Monitoring system for be used for anti-electricity-stealing |
| CN113221931A (en) * | 2020-12-23 | 2021-08-06 | 国网吉林省电力有限公司电力科学研究院 | Electricity stealing prevention intelligent identification method based on electricity utilization information acquisition big data analysis |
| CN112632152A (en) * | 2020-12-28 | 2021-04-09 | 国网冀北电力有限公司技能培训中心 | Circuit control system based on anti-electricity-stealing practical training room |
| CN113128024A (en) * | 2021-03-17 | 2021-07-16 | 国网山东省电力公司济南供电公司 | Low-voltage electricity stealing client based on big data analysis and electricity stealing means determining method |
| CN113128024B (en) * | 2021-03-17 | 2023-02-07 | 国网山东省电力公司济南供电公司 | Low-voltage electricity stealing client based on big data analysis and electricity stealing means determining method |
| CN113077174A (en) * | 2021-04-21 | 2021-07-06 | 国网福建省电力有限公司 | Method for studying and judging state of sewage disposal and treatment equipment based on curve discrete Frechst distance matching |
| CN113077174B (en) * | 2021-04-21 | 2022-08-05 | 国网福建省电力有限公司 | Method for studying and judging state of pollution discharge and treatment equipment based on curve discrete Frecher distance matching and computer readable storage medium |
| CN113111955A (en) * | 2021-04-21 | 2021-07-13 | 国网上海市电力公司 | Line loss abnormal data expert system and detection method |
| CN114076841A (en) * | 2021-11-12 | 2022-02-22 | 国网安徽省电力有限公司旌德县供电公司 | Electricity stealing behavior identification method and system based on electricity utilization information data |
| CN114881808A (en) * | 2022-04-01 | 2022-08-09 | 云南电网有限责任公司昭通供电局 | Electric power electricity stealing accurate identification method based on big data and electricity stealing prevention system |
| CN114881808B (en) * | 2022-04-01 | 2024-01-23 | 云南电网有限责任公司昭通供电局 | Big data-based accurate identification method for electric power larceny and electric power larceny prevention system |
| CN115292387A (en) * | 2022-08-18 | 2022-11-04 | 北京志翔科技股份有限公司 | Energy overrange use monitoring method based on multidimensional data analysis |
| CN116150239B (en) * | 2022-12-16 | 2023-09-22 | 彭州华润燃气有限公司 | Data mining method for gas stealing behavior |
| CN116150239A (en) * | 2022-12-16 | 2023-05-23 | 彭州华润燃气有限公司 | Data mining method for gas stealing behavior |
| CN117147959A (en) * | 2023-08-23 | 2023-12-01 | 广东电网有限责任公司佛山供电局 | Electricity larceny prevention analysis method and device |
| CN116777124A (en) * | 2023-08-24 | 2023-09-19 | 国网山东省电力公司临沂供电公司 | Power stealing monitoring method based on user power consumption behavior |
| CN116777124B (en) * | 2023-08-24 | 2023-11-07 | 国网山东省电力公司临沂供电公司 | Power stealing monitoring method based on user power consumption behavior |
| CN117131448A (en) * | 2023-08-25 | 2023-11-28 | 国网河南省电力公司渑池县供电公司 | Big data-based electricity stealing user intelligent identification system and method |
| CN117131448B (en) * | 2023-08-25 | 2024-04-16 | 国网河南省电力公司渑池县供电公司 | Big data-based electricity stealing user intelligent identification system and method |
| CN116976707A (en) * | 2023-09-22 | 2023-10-31 | 安徽融兆智能有限公司 | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition |
| CN116976707B (en) * | 2023-09-22 | 2023-12-26 | 安徽融兆智能有限公司 | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107742127B (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742127A (en) | A kind of improved anti-electricity-theft intelligent early-warning system and method | |
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN110223196A (en) | Analysis method of opposing electricity-stealing based on typical industry feature database and sample database of opposing electricity-stealing | |
| CN110263846A (en) | The method for diagnosing faults for being excavated and being learnt based on fault data depth | |
| CN110458230A (en) | A kind of distribution transforming based on the fusion of more criterions is with adopting data exception discriminating method | |
| CN105374209B (en) | A kind of urban area road network running status characteristics information extraction method | |
| CN110458195B (en) | Abnormal data discrimination method based on multi-criterion fusion | |
| CN103678766A (en) | Abnormal electricity consumption client detection method based on PSO algorithm | |
| CN108765004A (en) | A method of user's electricity stealing is identified based on data mining | |
| CN110222991A (en) | Metering device method for diagnosing faults based on RF-GBDT | |
| CN110458444A (en) | A kind of low-voltage platform area operating status multidimensional influence factor integrated evaluating method and system | |
| CN111179109A (en) | Electricity consumption data processing method for detecting elderly people living alone | |
| CN109947815B (en) | Power theft identification method based on outlier algorithm | |
| CN105069469A (en) | Data flow detection method based on fuzzy C-means clustering algorithm and entropy theory | |
| CN109491339B (en) | Big data-based substation equipment running state early warning system | |
| CN111081379A (en) | Disease probability decision method and system | |
| CN108154256A (en) | The determining method and device of forecasting risk value, storage medium | |
| CN110490486B (en) | Enterprise big data management system | |
| Hartmann et al. | Suspicious electric consumption detection based on multi-profiling using live machine learning | |
| Zhou et al. | A dynamic energy benchmarking methodology on room level for energy performance evaluation | |
| CN110689140A (en) | Method for intelligently managing rail transit alarm data through big data | |
| CN109977984A (en) | Stealing user's judgment method based on support vector machines | |
| CN115545342A (en) | Risk prediction method and system for enterprise electric charge recovery | |
| CN115062686A (en) | Multi-KPI (Key performance indicator) time sequence abnormity detection method and system based on multi-angle features | |
| CN108493933A (en) | A kind of Characteristics of Electric Load method for digging based on depth decision Tree algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |